Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.9126. Min Act: -0.1700
Data Index: 5561431 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.7563. Min Act: -0.1700
Data Index: 2040909 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.6626. Min Act: -0.1700
Data Index: 3780637 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.5688. Min Act: -0.1700
Data Index: 934805 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.3501. Min Act: -0.1700
Data Index: 2812280 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.3188. Min Act: -0.1700
Data Index: 810490 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.2563. Min Act: -0.1700
Data Index: 713339 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.2563. Min Act: -0.1700
Data Index: 2318480 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.2563. Min Act: -0.1700
Data Index: 8302850 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.1938. Min Act: -0.1700
Data Index: 6423250 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.1938. Min Act: -0.1700
Data Index: 3901817 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.1626. Min Act: -0.1700
Data Index: 2721040 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.1938. Min Act: -0.1700
Data Index: 8581817 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.1626. Min Act: -0.1700
Data Index: 4848586 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.1313. Min Act: -0.1700
Data Index: 8561249 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.1001. Min Act: -0.1700
Data Index: 2266521 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.1001. Min Act: -0.1700
Data Index: 1979680 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.0688. Min Act: -0.1700
Data Index: 6099325 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.1001. Min Act: -0.1700
Data Index: 6118726 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9126. Min Range: -7.9126
Max Act: 7.1001. Min Act: -0.1700
Data Index: 441965 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19